Key result
Quantitative EEG differentiates Parkinson's disease from healthy controls with an AUC of ~0.80.
Why the study?
Certain QEEG parameters have been associated with dementia in Parkinson's and Alzheimer's disease, and some depend on disease stage, but optimal features to distinguish PD patients from healthy individuals were unclear.
Can Quantitative EEG (QEEG) measures combined with machine learning differentiate Parkinson's disease patients from healthy controls?
Case-Control (n=91)
No
Can Quantitative EEG (QEEG) measures combined with machine learning differentiate Parkinson's disease patients from healthy controls?
Effect estimate: AUC 0.80
Penalized regression methods like LASSO can effectively select a small subset of QEEG features to differentiate Parkinson's disease patients from healthy controls.
No takes yet. Share an insight, caveat, or question.
May support qEEG for PD differentiation; hypothesis-generating and requires validation before clinical adoption.
Chaturvedi et al. (2017) conducted a case-control in Parkinson's Disease (n=91). Quantitative EEG (QEEG) features vs. Healthy controls was evaluated on Classification accuracy (AUC) for differentiating PD patients from healthy controls (AUC 0.80). Quantitative EEG measures, particularly theta power in the temporal left region and alpha1/theta ratio in the central left region, differentiated Parkinson's disease patients from healthy controls with an AUC of 0.80 using Random Forest.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: